• The Journal of the Korea Contents Association
• /
• v.18 no.12
• /
• pp.639-645
• /
• 2018

The objective of this research was to compare the precision of scanning the digital abutment impression and gypsum model according to 3-dimensional superimposing different skills. There were made with the abutment impression and gypsum model of a maxillary 1st premolar, blue light scanner scanned to obtain the stereolithography (STL) file. After the same process was performed 10 more times without moving them on the scanner table about the abutment impression and gypsum model, respectively (n=11, per types). By superimposing the date of scanning the abutment impression and gypsum model used with no control and best-fit-alignment skills, 10 color-difference maps and root mean square (RMS) data were obtained. The independent t-test was performed to compare RMS data between the each other groups (${\alpha}=0.05$). In the scanning abutment impressions, $RMS{\pm}SD$ of no control, best-fit-alignment showed $6.86{\pm}0.94$, $5.04{\pm}0.24$. in the scanning gypsum model, $4.98{\pm}1.16$, $3.39{\pm}0.07$, all groups showed a significant difference (P<0.001). Trough the this study's result, not only best-fit-alignment but no control is used with digital dental computer-aided design/computer-aided manufacturing (CAD/CAM) research and clinical part.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.11-20
• /
• 2019

In this study, a novel virtual reality (VR) experience environment is proposed for enabling walking adaptation of visually impaired people. The core of proposed VR environment is based on immersive walking interactions and deep learning based braille blocks recognition. To provide a realistic walking experience from the perspective of visually impaired people, a tracker-based walking process is designed for determining the walking state by detecting marching in place, and a controller-based VR white cane is developed that serves as the walking assistance tool for visually impaired people. Additionally, a learning model is developed for conducting comprehensive decision-making by recognizing and responding to braille blocks situated on roads that are followed during the course of directions provided by the VR white cane. Based on the same, a VR application comprising an outdoor urban environment is designed for analyzing the VR walking environment experience. An experimental survey and performance analysis were also conducted for the participants. Obtained results corroborate that the proposed VR walking environment provides a presence of high-level walking experience from the perspective of visually impaired people. Furthermore, the results verify that the proposed learning algorithm and process can recognize braille blocks situated on sidewalks and roadways with high accuracy.

• Journal of Digital Convergence
• /
• v.17 no.9
• /
• pp.185-192
• /
• 2019

The introduction of smart technology provides accuracy, safety, and efficiency to both physicians and patients. Although interest in a clear aligner is increasing among users worldwide, the current clear aligner requires a visit to the hospital every one or two weeks for replacement, which is a very cumbersome process. There is also confusion among dentists and patients because about 40 to 80 devices are made, and calibration is done based on the order and duration of the clear aligner. Therefore, this study designed and developed a clear aligner management system so that communication between the patient and dentist can be smoothly performed by inserting the QR code into the transparent correction device. As a result, the size of the QR code was recognized as $6{\ast}6mm^2$ which can be used in the oral and the recognition distance was 100% within 12 cm. Since the dentist can remotely manage the patient with the proposed system and improve the correction effect, it is possible to manage patients abroad, as well as domestically.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.21 no.3
• /
• pp.347-362
• /
• 2019

Underground excavation using TBM machines has been increasing to reduce complaints caused by noise, vibration, and traffic congestion resulted from the urban underground construction in Korea. However, TBM excavation design and construction still need improvement because those are based on standards of the technologically advanced countries (e.g., Japan, Germany) that do not consider geological environment in Korea at all. Above all, although TBM performance is a main factor determining the TBM machine type, duration and cost of the construction, it is estimated by only using UCS (uniaxial compressive strength) as the ground parameters and it often does not match the actual field conditions. This study was carried out as part of efforts to predict penetration rate suitable for Korean ground conditions. The effective parameters were defined through the correlation analysis between the penetration rate and the geotechnical parameters or TBM performance parameters. The effective parameters were then used as variables of the multiple regression analysis to derive a regression model for predicting TBM penetration rate. As a result, the regression model was estimated by UCS and joint spacing and showed a good agreement with field penetration rate measured during TBM excavation. However, when this model was applied to another site in Korea, the prediction accuracy was slightly reduced. Therefore, in order to overcome the limitation of the regression model, further studies are required to obtain a generalized prediction model which is not restricted by the field conditions.

• Journal of Digital Convergence
• /
• v.17 no.1
• /
• pp.209-217
• /
• 2019

In this paper, the purpose of this paper is to lay the foundation for the search system by using and building an online search engine suitable for the search domain and enabling search, conversion, integration and sharing of information. It is to use the ontology to infer hierarchical relationships, deduce objects based on that layer, and extract attributes to search areas that are relevant to the data that the user wants. In order to search for information in this way, the information search system was implemented by entering key words related to 'qualifications'. The implemented system arranged the meaning and relationship of each attribute online so that the general public can search information quickly, easily, and accurately. In addition, the implementation results were compared with two different search engines. Comparable search engines are Naver and Daum, the two major search engines. The search engine of this study, which was built using an ontology suitable for the search domain to perform searches using the semantic web, was evaluated to have excellent results. However, it is thought that a more formalized online location is necessary to increase the accuracy and reliability of search engines and to include more comprehensive categories of search terms.

• Korean Chemical Engineering Research
• /
• v.59 no.2
• /
• pp.209-218
• /
• 2021

First principle-based modeling studies have been performed to improve the heat exchange efficiency of ORV and optimize operation, but the heat transfer coefficient of ORV is an irregular system according to time and location, and it undergoes a complex modeling process. In this study, FNN, LSTM, and AutoML-based modeling were performed to confirm the effectiveness of data-based modeling for complex systems. The prediction accuracy indicated high performance in the order of LSTM > AutoML > FNN in MSE. The performance of AutoML, an automatic design method for machine learning models, was superior to developed FNN, and the total time required for model development was 1/15 compared to LSTM, showing the possibility of using AutoML. The prediction of NG and seawater discharged temperatures using LSTM and AutoML showed an error of less than 0.5K. Using the predictive model, real-time optimization of the amount of LNG vaporized that can be processed using ORV in winter is performed, confirming that up to 23.5% of LNG can be additionally processed, and an ORV optimal operation guideline based on the developed dynamic prediction model was presented.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.9 no.3
• /
• pp.303-310
• /
• 2021

Cracks in bridges are important factors that indicate the condition of bridges and should be monitored periodically. However, a visual inspection conducted by a human expert has problems in cost, time, and reliability. Therefore, in recent years, researches to apply a deep learning model are started to be conducted. Deep learning requires sufficient data on the situations to be predicted, but bridge crack data is relatively difficult to obtain. In particular, it is difficult to collect a large amount of crack data in a specific situation because the shape of bridge cracks may vary depending on the bridge's design, location, and construction method. This study developed a crack detection model that generates and trains insufficient crack data through a Generative Adversarial Network. GAN successfully generated data statistically similar to the given crack data, and accordingly, crack detection was possible with about 3% higher accuracy when using the generated image than when the generated image was not used. This approach is expected to effectively improve the performance of the detection model as it is applied when crack detection on bridges is required, though there is not enough data, also when there is relatively little or much data f or one class.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.23-35
• /
• 2021

In the era of the 4th industrial revolution, smart factories have received great attention, where production and manufacturing technology and ICT converge. With the development of IoT technology and big data, automation of production systems has become possible. In the advanced manufacturing industry, production systems are subject to unscheduled performance degradation and downtime, and there is a demand to reduce safety risks by detecting and reparing potential errors as soon as possible. This study designs a model based on supervised and unsupervised learning for detecting anomalies. The accuracy of XGBoost, LightGBM, and CNN models was compared as a supervised learning analysis method. Through the evaluation index based on the confusion matrix, it was confirmed that LightGBM is most predictive (97%). In addition, as an unsupervised learning analysis method, MD, AE, and LSTM-AE models were constructed. Comparing three unsupervised learning analysis methods, the LSTM-AE model detected 75% of anomalies and showed the best performance. This study aims to contribute to the advancement of the smart factory by combining supervised and unsupervised learning techniques to accurately diagnose equipment failures and predict when abnormal situations occur, thereby laying the foundation for preemptive responses to abnormal situations. do.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.33 no.3
• /
• pp.122-130
• /
• 2021

A wind-speed estimation at the arbitrary elevations is key component for the design of the offshore wind energy structures and the computation of the wind-wave generation. However, the wind-speed estimation of the target elevation has been carried out by using the typical functions and their typical parameters, e.g., power and logarithmic functions because the available wind speed data is limited to the specific elevation, such as 2~3m, 10 m, and so on. In this study, the parameters of the vertical profile functions are estimated with optimal and analyzed the parameter ranges using the HeMOSU-1 platform wind data monitored at the eight different locations. The results show that the mean value of the exponent of the power function is 0.1, which is significantly lower than the typically recommended value, 0.14. The values of the exponent, the friction velocity, and the roughness parameters are in the ranges 0.0~0.3, 0~10 (m/s), and 0.0~1.0 (m), respectively. The parameter ranges differ from the typical ranges because the atmospheric stability condition is assumed as the neutral condition. To improve the estimation accuracy, the atmospheric condition should be considered, and a more general (non-linear) vertical profile functions should be introduced to fit the diverse profile patterns and parameters.

• Journal of Broadcast Engineering
• /
• v.26 no.3
• /
• pp.269-282
• /
• 2021

As the distribution of 3D content such as augmented reality and virtual reality increases, the importance of real-time computer animation technology is increasing. However, the computer animation process consists mostly of manual or marker-attaching motion capture, which requires a very long time for experienced professionals to obtain realistic images. To solve these problems, animation production systems and algorithms based on deep learning model and sensors have recently emerged. Thus, in this paper, we study four methods of implementing natural human movement in deep learning model and kinect camera-based animation production systems. Each method is chosen considering its environmental characteristics and accuracy. The first method uses a Kinect camera. The second method uses a Kinect camera and a calibration algorithm. The third method uses deep learning model. The fourth method uses deep learning model and kinect. Experiments with the proposed method showed that the fourth method of deep learning model and using the Kinect simultaneously showed the best results compared to other methods.